jbolda

@app.route('/login/<provider_name>', methods=['GET', 'POST'])
@authomatic.login('g')
@requires_ssl
def login(provider_name):
    if g.user is not None and g.user.is_authenticated():
        return redirect(url_for('index'))
    if authomatic.result:
        if authomatic.result.error:
            return 'Something went wrong: {0}'.format(authomatic.result.error.message)
        if authomatic.result.user:

drgarcia1986

# !/usr/bin/env python
# -*- coding: utf-8 -*-
__author__ = 'Diego Garcia'

import tornado.web
import tornado.ioloop
import oauth2.tokengenerator
import oauth2.grant
import oauth2.store.redisdb
import oauth2.store.mongodb

stalkerg

import hashlib
import hmac
import mimetypes

import binascii
from calendar import timegm
from datetime import datetime
import time
from email.utils import formatdate
from urllib.parse import quote, urlparse

dannguyen

Extracting financial disclosure reports and police blotter narratives using OpenAI's Structured Output

tl;dr this demo shows how to call OpenAI's gpt-4o-mini model, provide it with URL of a screenshot of a document, and extract data that follows a schema you define. The results are pretty solid even with little effort in defining the data — and no effort doing data prep. OpenAI's API could be a cost-efficient tool for large scale data gathering projects involving public documents.

OpenAI announced Structured Outputs for its API, a feature that allows users to specify the fields and schema of extracted data, and guarantees that the JSON output will follow that specification.

For example, given a Congressional financial disclosure report, with assets defined in a table like this: